Quantum optimization algorithm based on multistep quantum computation

TL;DR

This paper introduces a multistep quantum algorithm for continuous optimization that reduces search space exponentially and mitigates local minima trapping, enabling efficient global minimum finding.

Contribution

The paper presents a novel multistep quantum computation approach that systematically reduces the search space for optimization problems with continuous variables.

Findings

Search space reduction is exponential at each step

Algorithm mitigates local minima trapping

Tested successfully on continuous functions

Abstract

We present a quantum algorithm for finding the minimum of a function based on multistep quantum computation and apply it for optimization problems with continuous variables, in which the variables of the problem are discretized to form the state space of the problem. Usually the cost for solving the problem increases dramatically with the size of the problem. In this algorithm, the dimension of the search space of the problem can be reduced exponentially step by step. We construct a sequence of Hamiltonians such that the search space of a Hamiltonian is nested in that of the previous one. By applying a multistep quantum computation process, the optimal vector is finally located in a small state space and can be determined efficiently. One of the most difficult problems in optimization is that a trial vector is trapped in a deep local minimum while the global minimum is missed, this problem can be alleviated in our algorithm and the runtime is proportional to the number of the steps of the algorithm, provided certain conditions are satisfied. We have tested the algorithm for some continuous test functions.